© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1155
    Prev
    Next
    INDEX
    Explanations

    auxiliary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stick
    -0.79
     Stick
    -0.60
    DR
    -0.59
     hand
    -0.53
     DR
    -0.52
     #
    -0.52
    ally
    -0.50
     @
    -0.49
    stick
    -0.46
    はじめに
    -0.45
    POSITIVE LOGITS
    脚注の使い方
    0.90
     cardiaque
    0.81
     suprême
    0.80
     الرياضيه
    0.78
     Theſe
    0.77
     énergétique
    0.77
     chré
    0.75
     المعيارى
    0.75
     eût
    0.74
     méri
    0.74
    Activations Density 0.171%

    No Known Activations